Automated Entity Classification in Video Using Soft Biometrics Navy SBIR FY2008.1 Sol No.: Navy SBIR FY2008.1 Topic No.: N08-077 Topic Title: Automated Entity Classification in Video Using Soft Biometrics Proposal No.: N081-077-0647 Firm: ISCA Technologies, Inc. PO Box 5266 Riverside, California 92517-5266 Contact: Agenor Mafra-Neto Phone: (951) 686-5008 Web Site: www.iscatech.com Abstract: In this SBIR project we will develop an automated capability to quickly recognize and classify subjects in video imagery using soft biometrics. The system will have capability to translate video streams into probabilistic biometric metadata about the observed subjects (i.e. "With 82% confidence, subject is John Smith"). We intend to address both the accuracy and speed issues to produce a simple, intuitive and maintainable/upgradeable system which will allow real time and accurate searches of massive biometric archives. In essence our solutions will work by approximating the entire dataset in a small index which can be kept in main memory. At query time, this index is searched in milliseconds for an approximate answer, which is then confirmed by loading a small fraction of the original data from disk. A crucial observation is that if the index approximation has certain properties (the lower bounding lemma) we can guarantee that the result is the same one we would have gotten if we had done the slower brute force search. This system will allow for translation of descriptions of a person to a soft biometric metadata representation, allowing distributed and (possibly disparate) imagers to collaborate in inferring matches. Benefits: Anticipated Benefits/Potential Commercial Applications of the Research or Development. While the primary focus of work is addressing the needs specified in this call for proposals, our work has potential applications for many other domains apart from the obvious military and civilian law enforcement uses. Examples include: Loss Prevention: Classic biometrics are clearly not an option for retail stores, which can hardly demand customers register fingerprints as they enter a store. However soft biometrics does offer a possibility to identify habitual shoplifting offenders in the parking lot before they even get to the store. Positive Profiling/Extreme Personalization: Soft biometrics offer commercial possibilities which can be seen as a positive counterpoint to the negative loss prevention situation above. It is useful for stores to know their customers and their purchasing habits; hence the ubiquity of loyalty cards at supermarkets. The problem with loyalty cards is that the store can only recognize the customer at the point of sale, whereas they would really like to recognize him as he is browsing the aisles, so they can send a salesperson that is armed with knowledge of his recent purchases to assist him. We intend to explore such commercial possibilities. Return